工业级自托管文献+知识层，用于编码代理（Claude Code插件，底下MCP）
概览
一个自主机，作为一个MCP服务器交付。指向任何支持MCP的代理（Claude Code等），代理获得三项工具： - — 通过散文描述你的研究意图来发现文献;相关发现会自动导入（下载、OCR处理，全文存储在磁盘中）。- — 通过引用键 / DOI / arXiv id / 模糊标题查找论文;从返回路径逐字阅读全文。- — 向知识库提问，获得从知识图谱中提取的引用散文答案。 语料库无需精心调料：数十分钟内搜索→可查询知识，自我修复的输入队列，基于真实来源的引用答案。 预发布（封闭测试）。请参见docs/PRD.md了解范围，docs/architecture.md了解结构。这是工业级基础设施，不是玩具——安装前请阅读硬件底层。 Papervault 在本地运行自己的嵌入、重新排名和 OCR 模型。
概述（AI 翻译）
一个为编码代理提供自托管文献和知识层的编码代理，作为一个MCP交付 服务器。Claude Code、Codex CLI、Antigravity CLI/IDE 及其他 MCP 客户端共享三种工具：
| 工具 | 目的 |
|---|---|
search_papers |
发现自然语言研究意向的论文;提交独立承认的注册和背景采集。 |
get_paper |
解析引用键、DOI、arXiv ID 或模糊标题，并在可用时返回元数据及安全全文路径。 |
query |
从知识图谱中提取证据，并结合经过验证的论文引用综合答案。 |
版本0.10.11记录了重构后的搜索、目录和知识契约。 该产品处于预发布阶段（封闭测试）。请阅读PRD以了解范围， 边界建筑，安装指南 用于部署和基线 用于测定日期的测量。结构与重构计划 共同管理收藏完整性和有用的检索。
硬件地板（非可选）
支持的部署使用 Linux 和 CUDA，配备一块 **24GB 级别 NVIDIA 显卡（RTX 版） 3090/4090类）、Neo4j和PostgreSQL的Docker，以及一个操作符提供的 兼容OpenAI的大型语言模型终端和密钥。
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
papervault
A self-hosted literature and knowledge layer for coding agents, delivered as one MCP server. Claude Code, Codex CLI, Antigravity CLI/IDE and other MCP clients share three tools:
| Tool | Purpose |
|---|---|
search_papers |
Discover papers from a natural-language research intent; submit independently admitted registration and background acquisition. |
get_paper |
Resolve a citation key, DOI, arXiv ID or fuzzy title and return metadata plus a serve-safe full-text path when available. |
query |
Retrieve evidence from the knowledge graph and synthesize an answer with verified paper citations. |
Version 0.10.15 expands the default research domain and venue authority to include space computing alongside space physics and AI4Science. The product is pre-release (closed beta). Read the PRD for scope, architecture for boundaries, installation guide for deployment, and baselines for dated measurements. The constitution and refactor plan govern collection integrity and useful retrieval together.
Hardware floor (not optional)
The supported deployment uses Linux and CUDA, one 24 GB-class NVIDIA GPU (RTX
3090/4090 class), Docker for Neo4j and PostgreSQL, and an operator-supplied
OpenAI-compatible LLM endpoint and key. Embedding and reranking run locally; the
independent MinerU OCR service shares the GPU. The hardware floor is part of the
product contract. The factory domain pack is space physics, space computing, and AI4Science;
its search rubric, ontology, examples and instructions live in
src/papervault/domain/. Other domains need their own
configuration and evaluation gold sets.
Space computing covers orbital/satellite edge computing and computing constellations;
on-board AI and payload processing; spaceborne accelerators and radiation/fault tolerance;
space-air-ground computing and inter-satellite offloading/routing/scheduling; and orbital
data centers with compute energy management and thermal control. These additions use the
existing 11 entity types; the bundled pack remains named space_physics.
Quick start
Follow INSTALL.md for the complete setup:
cp .env.example .env # fill in the LLM endpoint, key and data roots
# External Docker volumes hold the backing stores; create once.
docker volume create ks-pgdata
docker volume create ks-neo4jdata
docker compose --env-file .env -f deploy/docker-compose.yml up -d
uv venv && uv pip install -e ".[grey]"
.venv/bin/papervault doctor
.venv/bin/papervault serve
Provision mineru-service separately at http://127.0.0.1:30000 (override with
MINERU_URL). papervault uses the official mineru-api HTTP task API through core
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手？先看 mcpskill.org 教程 →